Module aivis_engine_v2_sd_sdk_python.inference

Classes

class StateDetectionInference (handle, key)

Class for creating and handling state detection inference. This is your entry point for all inference operations.

Private constructor. To create new instances use:

• StateDetectionInference.create_by_training()
• StateDetectionInference.create_by_model()

Static methods

def create_by_model(cls, model_json: str, config_json: str) ‑> StateDetectionInference

@FlavourRequirement([Flavour.FULL, Flavour.INFERENCE])

Create state detection inference for given model and config.

Use StateDetectionInference.infer() to create predictions with this inference instance.

Parameters

model_json : str

Instance of DtoModel as JSON string

config_json : str

Instance of DtoInferenceConfig as JSON string

Returns

StateDetectionInference

Instance of state detection inference

def create_by_training(cls, training: StateDetectionTraining, config_json: str) ‑> StateDetectionInference

@FlavourRequirement([Flavour.FULL])

Create state detection inference for given training handle and config.

Use StateDetectionInference.infer() to create predictions with this inference instance.

Parameters

training : StateDetectionTraining

Instance of state detection training

config_json : str

DtoInferenceConfig as JSON string

Returns

StateDetectionInference

Instance of state detection inference

Methods

def destroy(self)

@FlavourRequirement([Flavour.FULL, Flavour.INFERENCE])

Destroy this state detection inference. It's always safe to destroy an inference. Internally the destruction only takes place after all references to this object have been released.

def get_data_specification(self) ‑> str

@FlavourRequirement([Flavour.FULL, Flavour.INFERENCE])

Get this inference's DtoInferenceDataSpecification

Returns

str

DtoInferenceDataSpecification as JSON string

def infer(self, data: StateDetectionData, timestamps: List[int]) ‑> List[DtoSegmentsFloatDataPoint]

@FlavourRequirement([Flavour.FULL, Flavour.INFERENCE])

Calculate segmented inference for given data context and timestamps. The result will be a list of DtoSegmentsFloatDataPoint instances corresponding to given timestamps. Make sure to fill the data context with all data needed for calculation. Check the model's DtoInferenceDataSpecification for needed signals and time ranges.

Parameters

data :  StateDetectionData

Instance of state detection data

timestamps : List[int]

List of timestamps

Returns

List[DtoSegmentsFloatDataPoint]

List of segmented float data points

def infer_with_next_normal(self, data: StateDetectionData, timestamps: List[int], config_json: str) ‑> List[DtoSegmentsFloatDataPointWithNextNormal]

@FlavourRequirement([Flavour.FULL, Flavour.INFERENCE])

For given data, timestamps, and next normal config, calculate for each segment the inference and the closest point that is normal as defined by the normal config. The result will be a list of DtoSegmentsFloatDataPointWithNextNormal instances corresponding to given timestamps. Make sure to fill the data context with all data needed for calculation. Check the model's DtoInferenceDataSpecification for needed signals and time ranges.

@experimental: Might change in future releases. See the user guide for known performance issues.

Parameters

data :  StateDetectionData

Instance of state detection data

timestamps : List[int]

List of timestamps

config_json : str

DtoNextNormalConfig as JSON string

Returns

List[DtoSegmentsFloatDataPointWithNextNormal]

List of segmented float data points enhanced with next normal data